Online speech dereverberation with time-varying assumption of acoustic transfer functions for teleconferencing systems

This paper deals with an online dereverberation technique for teleconferencing systems, which is robust against fluctuation of acoustic transfer functions (ATFs). The proposed method divides fluctuations into two classes. The first class is instantaneous fluctuation of the ATF of each speaker, e.g. movement of human head. Instead of the time-invariant assumption for the ATF in the conventional dereverberation techniques, the proposed method assumes that the ATF of each speaker is a probabilistic variable, and the dereverberated signal is obtained by integrating out of parameters related with the ATFs. The second class of fluctuations is fluctuation related with turn-taking of the active speaker. To be robust against the turn-taking, the proposed method utilizes multiple parameters which is estimated in different time-periods and selects the best parameter which maximizes the likelihood value at each time-frequency point. Experimental results under time-varying conditions show that the proposed method is effective.